Rankings / OpenAI
GPT 4o (2024-08-06)
released 2024-08-06
BenchAtlas Index
as of 2026-09-11
high effort
rank #375
6 families · 3 categories · medium
base configuration
rank #396
5 families · 3 categories · medium
Benchmark evidence
43 results
coding
| LiveCodeBench v5older version problems=279 · window_start=2024-08-01 | 30.0 % | independent | LiveCodeBench Leaderboard | |
| LiveCodeBench v6 problems=454 · window_start=2024-08-01 | 29.5 % | independent | LiveCodeBench Leaderboard |
external indices
| ECI | 129.4 points | independent | Epoch AI Benchmarking Hub |
factuality
| SimpleQA Verified | 26.0 % | independent | Epoch AI Benchmarking Hub 2026-08-31 |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1360.2 1352.2–1368.1 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1348.0 1342.6–1353.4 | community | LMArena Leaderboard Dataset | |
| Industry Life And Physical And Social Science (style control)older version arena=text · category=industry_life_and_physical_and_social_science · style_control=true | 1347.9 1339.8–1356.0 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1347.8 1335.3–1360.3 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1346.8 1340.1–1353.5 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1342.3 1328.4–1356.2 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1340.4 1333.5–1347.3 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1338.4 1330.0–1346.9 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1337.6 1329.9–1345.4 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1335.2 1330.9–1339.4 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1330.5 1319.7–1341.2 | community | LMArena Leaderboard Dataset | |
| Spanish (style control)older version arena=text · category=spanish · style_control=true | 1327.8 1300.7–1355.0 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1326.9 1319.0–1334.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1326.5 1320.1–1333.0 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1326.5 1317.9–1335.0 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1324.4 1316.1–1332.7 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1324.0 1315.2–1332.8 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1318.3 1312.5–1324.2 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1316.2 1310.6–1321.7 | community | LMArena Leaderboard Dataset | |
| German (style control)older version arena=text · category=german · style_control=true | 1312.9 1295.4–1330.4 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1312.8 1304.3–1321.3 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1311.2 1298.4–1324.0 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1308.5 1300.5–1316.6 | community | LMArena Leaderboard Dataset | |
| Industry Business And Management And Financial Operations (style control)older version arena=text · category=industry_business_and_management_and_financial_operations · style_control=true | 1301.9 1292.8–1311.0 | community | LMArena Leaderboard Dataset | |
| Japanese (style control)older version arena=text · category=japanese · style_control=true | 1291.9 1272.9–1310.9 | community | LMArena Leaderboard Dataset | |
| Korean (style control)older version arena=text · category=korean · style_control=true | 1288.8 1264.1–1313.5 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1285.7 1279.2–1292.2 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | 49.2 % | independent | Epoch AI Benchmarking Hub 2025-01-27 | |
| MMLU-Pro implementation=vals-ai | high effort | 74.1 % | independent | Vals AI |
multimodal
| MMMU implementation=vals-ai | high effort | 64.0 % | independent | Vals AI |
professional
| CorpFin | high effort | 39.4 % | independent | Vals AI |
| LegalBench | high effort | 80.1 % | independent | Vals AI |
| MedQA | high effort | 88.2 % | independent | Vals AI |
| TaxEval | high effort | 71.1 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | high effort | 14.0 % | independent | Vals AI |
| FrontierMath | 0.3 % | independent | Epoch AI Benchmarking Hub 2025-03-07 | |
| MATH-500 implementation=vals-ai | high effort | 75.2 % | independent | Vals AI |
| MATH Level 5 | 53.3 % | independent | Epoch AI Benchmarking Hub 2025-01-27 | |
| OTIS Mock AIME 2024–2025 | 6.4 % | independent | Epoch AI Benchmarking Hub 2025-02-25 |
Agent + model results
systems, not bare-model scores
| agent + model OpenCSG Starship Agentic Coder + GPT 4o (2024-08-06) | SWE-bench Lite | 39.7 % | unverified | SWE-bench Leaderboard |
| agent + model MASAI + GPT 4o (2024-08-06) | SWE-bench Verified | 32.6 % | unverified | SWE-bench Leaderboard |
| agent + model GUIRepair + GPT 4o (2024-08-06) | SWE-bench Multimodal | 30.4 % | community | SWE-bench Leaderboard |
| agent + model Agentless + GPT 4o (2024-08-06) | SWE-bench Lite | 29.7 % | unverified | SWE-bench Leaderboard |
| agent + model reproducedRG + GPT 4o (2024-08-06) | SWE-bench Lite | 28.0 % | unverified | SWE-bench Leaderboard |
| agent + model EPAM AI/Run Developer Agent + GPT 4o (2024-08-06) | SWE-bench Verified | 27.0 % | unverified | SWE-bench Leaderboard |
| agent + model HyperAgent + GPT 4o (2024-08-06) | SWE-bench Lite | 25.3 % | unverified | SWE-bench Leaderboard |
| agent + model Bytedance AutoSE (based on SWE-Agent) + GPT 4o (2024-08-06) | SWE-bench Lite | 21.7 % | unverified | SWE-bench Leaderboard |
| agent + model RAG + GPT 4o (2024-08-06) | SWE-bench Multimodal | 6.0 % | community | SWE-bench Leaderboard |
| agent + model Agentless + GPT 4o (2024-08-06) | SWE-bench Multimodal | 3.1 % | community | SWE-bench Leaderboard |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.